用判别式验证在有限算力下显著提升大模型推理准确率
Budget-aware Test-time Scaling via Discriminative Verification
- 采用判别式验证与自一致结合的混合策略，降低计算开销
- 固定算力下在AIME2025上比顶尖生成式验证高15.3%准确率
- 适合追求高效推理的工业级应用，尤其资源受限场景
测试时扩展是提升大语言模型在复杂推理任务中性能的有效策略。现有先进方法通常使用生成式验证器从候选解中选出最优解，但计算成本高昂，限制了实际应用。本文转向更注重预算的范式：判别式验证。通过全面的实证分析发现，尽管判别式验证器单独使用时表现较弱，但与自一致结合后形成高效的测试时扩展机制。在固定计算预算下，该混合方法在AIME2025上比当前最优的生成式验证高出15.3%的准确率。研究结果表明，对于实际应用，基于判别式验证的预算感知扩展不仅是自一致的‘免费’升级，更是比昂贵的生成式方法更有效、更高效的替代方案。代码已公开于https://github.com/wang-research-lab/verification。
原文摘要 · Abstract (English)
Test-time scaling is a powerful strategy for boosting the performance of large language models on complex reasoning tasks. While state-of-the-art approaches often employ generative verifiers to select the best solution from a pool of candidates, this method incurs prohibitive computational costs, limiting its practicality. In this work, we shift the focus to a more budget-aware paradigm: discriminative verification. We conduct a thorough empirical analysis and demonstrate that while discriminative verifiers may underperform in isolation, combining them with self-consistency in a hybrid approach creates a powerful and efficient test-time scaling mechanism. Notably, under a fixed compute budget, this hybrid approach surpasses state-of-the-art generative verification by a significant margin: achieving up to 15.3\% higher accuracy on AIME2025. Our findings establish that for practical, real-world applications, budget-aware scaling with discriminative verifiers is not only a "free" upgrade over self-consistency, but also a more effective and efficient alternative to costly generative techniques. Code is available at https://github.com/wang-research-lab/verification.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。